def start_job_service() -> None:
"""
Start Feast Job Service
"""
log_fmt = "%(asctime)s %(levelname)s %(message)s"
logging.basicConfig(level=logging.INFO, format=log_fmt)
client = feast.Client()
if client._config.getboolean(opt.JOB_SERVICE_ENABLE_CONTROL_LOOP):
# Start the control loop thread only if it's enabled from configs
thread = threading.Thread(target=start_control_loop, daemon=True)
thread.start()
server = grpc.server(ThreadPoolExecutor(),
interceptors=(LoggingInterceptor(), ))
JobService_pb2_grpc.add_JobServiceServicer_to_server(
JobServiceServicer(client), server)
HealthService_pb2_grpc.add_HealthServicer_to_server(
HealthServicer(), server)
server.add_insecure_port("[::]:6568")
server.start()
logging.info("Feast Job Service is listening on port :6568")
server.wait_for_termination()
def __init__(
self,
datastore: str,
credential_path: str,
table_name: str,
ds: str,
epochs: int,
batch_size: int,
chunk_size: int,
exclude_features: List[str],
table_sample_percent: float,
test_split_percent: float,
skip_small_batches: bool,
faucet_core_url: str,
faucet_batch_serving_url: str,
faucet_project: str,
):
# Intialize clients & set table properties
self.client = self._get_client(credential_path)
self.table_name = table_name
self.exclude_features = exclude_features
if faucet_core_url is not None:
assert faucet_batch_serving_url is not None
assert faucet_project is not None
self.feast_client = feast.Client(
core_url=faucet_core_url, serving_url=faucet_batch_serving_url)
self.feast_client.set_project(faucet_project)
# Figure out sampling + train & test
self.max_row_filter = table_sample_percent / 100
self.train_set_filter = self.max_row_filter * (
1 - test_split_percent / 100)
# Generate queries for the training & test set
self.train_query, self.eval_query = self._build_train_and_eval_queries(
ds)
# Create query jobs to create temp tables (non-blocking)
self.train_query_job = self._create_tmp_table(train=True)
self.eval_query_job = self._create_tmp_table(train=False)
# Minibatch settings
self.batch_size = batch_size
self.skip_small_batches = skip_small_batches
# Chunk settings
self.chunk_size = chunk_size
assert (
chunk_size % batch_size == 0
), f"Chunk size: {chunk_size} must be multiple of batch size: {batch_size}."
# Epoch settings
self.epochs = epochs
self.current_epoch_num = 0
# Preprocessing specifications & preprocessor net
self.preproc_specifications = None
self.preprocessor_net = None
def start_control_loop() -> None:
"""Starts control loop that continuously ensures that correct jobs are being run.
Currently this affects only the stream ingestion jobs. Please refer to
ensure_stream_ingestion_jobs for full documentation on how the check works.
"""
logging.info(
"Feast Job Service is starting a control loop in a background thread, "
"which will ensure that stream ingestion jobs are successfully running."
)
try:
client = feast.Client()
while True:
ensure_stream_ingestion_jobs(client, all_projects=True)
time.sleep(1)
except Exception:
traceback.print_exc()
finally:
# Send interrupt signal to the main thread to kill the server if control loop fails
os.kill(os.getpid(), signal.SIGINT)
def __init__(self):
print("Connecting to feast", feast_options)
for k, v in feast_options.items():
os.environ[k] = v
self.feast_client = feast.Client()
def __init__(self):
self.client = feast.Client()
